Automatic Speech Recognition
Transformers
Safetensors
German
hubert
audio
ctc
ipa
pronunciation-scoring
german
robust-asr
Eval Results (legacy)
Instructions to use q1805/hubert_large-german-IPA-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use q1805/hubert_large-german-IPA-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="q1805/hubert_large-german-IPA-v2")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("q1805/hubert_large-german-IPA-v2") model = AutoModelForCTC.from_pretrained("q1805/hubert_large-german-IPA-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 299 Bytes
a9dec77 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | {
"feature_extractor": {
"do_normalize": true,
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
"feature_size": 1,
"padding_side": "right",
"padding_value": 0.0,
"return_attention_mask": true,
"sampling_rate": 16000
},
"processor_class": "Wav2Vec2Processor"
}
|